A General Knowledge Injection Framework for ICD Coding
This addresses the challenge of long-tail distribution and lack of annotations in medical coding for healthcare applications, though it appears incremental by combining existing knowledge types into a unified framework.
The paper tackles the problem of ICD coding, which assigns medical codes to text, by proposing GKI-ICD, a general framework that integrates three types of knowledge (ICD Description, Synonym, and Hierarchy) to improve performance, achieving state-of-the-art results on most metrics in benchmarks.
ICD Coding aims to assign a wide range of medical codes to a medical text document, which is a popular and challenging task in the healthcare domain. To alleviate the problems of long-tail distribution and the lack of annotations of code-specific evidence, many previous works have proposed incorporating code knowledge to improve coding performance. However, existing methods often focus on a single type of knowledge and design specialized modules that are complex and incompatible with each other, thereby limiting their scalability and effectiveness. To address this issue, we propose GKI-ICD, a novel, general knowledge injection framework that integrates three key types of knowledge, namely ICD Description, ICD Synonym, and ICD Hierarchy, without specialized design of additional modules. The comprehensive utilization of the above knowledge, which exhibits both differences and complementarity, can effectively enhance the ICD coding performance. Extensive experiments on existing popular ICD coding benchmarks demonstrate the effectiveness of GKI-ICD, which achieves the state-of-the-art performance on most evaluation metrics. Code is available at https://github.com/xuzhang0112/GKI-ICD.